Finite-Horizon Distributed H∞ Fault Estimation for Time-Varying Systems in Sensor Networks: A Krein-Space Approach★

In this paper, the finite-horizon distributed H∞ fault estimation problem is investigated for a class of linear discrete time-varying systems in sensor networks. Sensor nodes are distributed according to a given network topology and each sensor receives the information from both the system and its neighbors. A set of measurement models is established for each sensor node that describes all the available information from the node and its neighbors. The distributed H∞ fault estimation problem addressed is first transformed into an optimization issue of a certain indefinite quadratic form. Then, by employing innovation analysis and projection theory in Krein spaces, the desired distributed H∞ fault estimators are designed in terms of the solution to a set of recursive equations. Finally, an illustrative example is presented to show the effectiveness of the proposed distributed fault estimation scheme.